Page 31 - Contributed Paper Session (CPS) - Volume 5

CPS657 Folorunso Serifat A. et al.
Table 1: Descriptive Statistics of the Survival Time of Ovarian Cancer
Min 1 Median Mean 3 Max Skewness Kurtosis
1 24 48 45.05 57 159 1.395 7.339

Table 2: Model evaluation for the ovarian Cancer
Model AIC -2loglike ̃ c Var(c)
̃
Weibull 216.8845 210.8846 2.4400 68.200 60.0706 0.2890 0.096810
Lognorm 205.9782 199.9782 4.0400 0.3280 57.9748 0.3712 0.004261
Llogis 203.2744 197.2744 5.9701 56.207 56.8649 0.1810 0.287870
GenGamma 206.2014 198.2014 3.9635 0.3017 20.90111 0.1084 0.005230
GGG 199.2353 194.4712 7.5240 15.2460 11.8201 0.8207 0.000125

Weibull: Weibull Mixture Cure Model Lognorm: Log-Normal Mixture
Cure Model
Llogis: LogLogistics Mixture Cure Model GenGamma: Generalised
Gamma Mixture Cure Model
GGG: Gamma Generalised Gamma Mixture Cure Model ̃: Median,
̃
: median time to cure

Simulated Data
The simulation study utilized data based on continuous uniform
distribution with = 100 and = 1 using sample of sizes (n) of 10, 20, and 50
each in 50, 100, and 500 replicates (r). In other to compare the models, we
consider MSE, RMSE and Absolute BIAS as the criteria to check for the flexible
best across the replications considers. The lower the value of these criteria, the
more efficient is the model.

20 | I S I W S C 2 0 1 9